LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: David Stevens <stevensd@chromium.org>
To: Robin Murphy <robin.murphy@arm.com>
Cc: Christoph Hellwig <hch@lst.de>, Joerg Roedel <joro@8bytes.org>,
	Will Deacon <will@kernel.org>,
	Sergey Senozhatsky <senozhatsky@chromium.org>,
	Lu Baolu <baolu.lu@linux.intel.com>,
	iommu@lists.linux-foundation.org, linux-kernel@vger.kernel.org,
	David Stevens <stevensd@chromium.org>
Subject: [PATCH v2 1/9] Revert "iommu: Allow the dma-iommu api to use bounce buffers"
Date: Fri,  6 Aug 2021 19:34:15 +0900	[thread overview]
Message-ID: <20210806103423.3341285-2-stevensd@google.com> (raw)
In-Reply-To: <20210806103423.3341285-1-stevensd@google.com>

From: David Stevens <stevensd@chromium.org>

A new pooled bounce buffer implementation will be added to reduce IOMMU
interactions on platforms with slow IOMMUs. The new implementation can
also support using bounce buffers with untrusted devices, so the current
basic bounce buffer support can be reverted.

This reverts commit 82612d66d51d3bacdd789e31d2e875d2494b7514.

Signed-off-by: David Stevens <stevensd@chromium.org>
---
 drivers/iommu/dma-iommu.c | 152 ++++----------------------------------
 1 file changed, 13 insertions(+), 139 deletions(-)

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 98ba927aee1a..1491b5450246 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -20,11 +20,9 @@
 #include <linux/mm.h>
 #include <linux/mutex.h>
 #include <linux/pci.h>
-#include <linux/swiotlb.h>
 #include <linux/scatterlist.h>
 #include <linux/vmalloc.h>
 #include <linux/crash_dump.h>
-#include <linux/dma-direct.h>
 
 struct iommu_dma_msi_page {
 	struct list_head	list;
@@ -493,23 +491,6 @@ static void __iommu_dma_unmap(struct device *dev, dma_addr_t dma_addr,
 	iommu_dma_free_iova(cookie, dma_addr, size, iotlb_gather.freelist);
 }
 
-static void __iommu_dma_unmap_swiotlb(struct device *dev, dma_addr_t dma_addr,
-		size_t size, enum dma_data_direction dir,
-		unsigned long attrs)
-{
-	struct iommu_domain *domain = iommu_get_dma_domain(dev);
-	phys_addr_t phys;
-
-	phys = iommu_iova_to_phys(domain, dma_addr);
-	if (WARN_ON(!phys))
-		return;
-
-	__iommu_dma_unmap(dev, dma_addr, size);
-
-	if (unlikely(is_swiotlb_buffer(phys)))
-		swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs);
-}
-
 static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
 		size_t size, int prot, u64 dma_mask)
 {
@@ -536,52 +517,6 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
 	return iova + iova_off;
 }
 
-static dma_addr_t __iommu_dma_map_swiotlb(struct device *dev, phys_addr_t phys,
-		size_t org_size, dma_addr_t dma_mask, bool coherent,
-		enum dma_data_direction dir, unsigned long attrs)
-{
-	int prot = dma_info_to_prot(dir, coherent, attrs);
-	struct iommu_domain *domain = iommu_get_dma_domain(dev);
-	struct iommu_dma_cookie *cookie = domain->iova_cookie;
-	struct iova_domain *iovad = &cookie->iovad;
-	size_t aligned_size = org_size;
-	void *padding_start;
-	size_t padding_size;
-	dma_addr_t iova;
-
-	/*
-	 * If both the physical buffer start address and size are
-	 * page aligned, we don't need to use a bounce page.
-	 */
-	if (IS_ENABLED(CONFIG_SWIOTLB) && dev_is_untrusted(dev) &&
-	    iova_offset(iovad, phys | org_size)) {
-		aligned_size = iova_align(iovad, org_size);
-		phys = swiotlb_tbl_map_single(dev, phys, org_size,
-					      aligned_size, dir, attrs);
-
-		if (phys == DMA_MAPPING_ERROR)
-			return DMA_MAPPING_ERROR;
-
-		/* Cleanup the padding area. */
-		padding_start = phys_to_virt(phys);
-		padding_size = aligned_size;
-
-		if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
-		    (dir == DMA_TO_DEVICE ||
-		     dir == DMA_BIDIRECTIONAL)) {
-			padding_start += org_size;
-			padding_size -= org_size;
-		}
-
-		memset(padding_start, 0, padding_size);
-	}
-
-	iova = __iommu_dma_map(dev, phys, aligned_size, prot, dma_mask);
-	if (iova == DMA_MAPPING_ERROR && is_swiotlb_buffer(phys))
-		swiotlb_tbl_unmap_single(dev, phys, org_size, dir, attrs);
-	return iova;
-}
-
 static void __iommu_dma_free_pages(struct page **pages, int count)
 {
 	while (count--)
@@ -776,15 +711,11 @@ static void iommu_dma_sync_single_for_cpu(struct device *dev,
 {
 	phys_addr_t phys;
 
-	if (dev_is_dma_coherent(dev) && !dev_is_untrusted(dev))
+	if (dev_is_dma_coherent(dev))
 		return;
 
 	phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dma_handle);
-	if (!dev_is_dma_coherent(dev))
-		arch_sync_dma_for_cpu(phys, size, dir);
-
-	if (is_swiotlb_buffer(phys))
-		swiotlb_sync_single_for_cpu(dev, phys, size, dir);
+	arch_sync_dma_for_cpu(phys, size, dir);
 }
 
 static void iommu_dma_sync_single_for_device(struct device *dev,
@@ -792,15 +723,11 @@ static void iommu_dma_sync_single_for_device(struct device *dev,
 {
 	phys_addr_t phys;
 
-	if (dev_is_dma_coherent(dev) && !dev_is_untrusted(dev))
+	if (dev_is_dma_coherent(dev))
 		return;
 
 	phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dma_handle);
-	if (is_swiotlb_buffer(phys))
-		swiotlb_sync_single_for_device(dev, phys, size, dir);
-
-	if (!dev_is_dma_coherent(dev))
-		arch_sync_dma_for_device(phys, size, dir);
+	arch_sync_dma_for_device(phys, size, dir);
 }
 
 static void iommu_dma_sync_sg_for_cpu(struct device *dev,
@@ -810,17 +737,11 @@ static void iommu_dma_sync_sg_for_cpu(struct device *dev,
 	struct scatterlist *sg;
 	int i;
 
-	if (dev_is_dma_coherent(dev) && !dev_is_untrusted(dev))
+	if (dev_is_dma_coherent(dev))
 		return;
 
-	for_each_sg(sgl, sg, nelems, i) {
-		if (!dev_is_dma_coherent(dev))
-			arch_sync_dma_for_cpu(sg_phys(sg), sg->length, dir);
-
-		if (is_swiotlb_buffer(sg_phys(sg)))
-			swiotlb_sync_single_for_cpu(dev, sg_phys(sg),
-						    sg->length, dir);
-	}
+	for_each_sg(sgl, sg, nelems, i)
+		arch_sync_dma_for_cpu(sg_phys(sg), sg->length, dir);
 }
 
 static void iommu_dma_sync_sg_for_device(struct device *dev,
@@ -830,17 +751,11 @@ static void iommu_dma_sync_sg_for_device(struct device *dev,
 	struct scatterlist *sg;
 	int i;
 
-	if (dev_is_dma_coherent(dev) && !dev_is_untrusted(dev))
+	if (dev_is_dma_coherent(dev))
 		return;
 
-	for_each_sg(sgl, sg, nelems, i) {
-		if (is_swiotlb_buffer(sg_phys(sg)))
-			swiotlb_sync_single_for_device(dev, sg_phys(sg),
-						       sg->length, dir);
-
-		if (!dev_is_dma_coherent(dev))
-			arch_sync_dma_for_device(sg_phys(sg), sg->length, dir);
-	}
+	for_each_sg(sgl, sg, nelems, i)
+		arch_sync_dma_for_device(sg_phys(sg), sg->length, dir);
 }
 
 static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
@@ -849,10 +764,10 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
 {
 	phys_addr_t phys = page_to_phys(page) + offset;
 	bool coherent = dev_is_dma_coherent(dev);
+	int prot = dma_info_to_prot(dir, coherent, attrs);
 	dma_addr_t dma_handle;
 
-	dma_handle = __iommu_dma_map_swiotlb(dev, phys, size, dma_get_mask(dev),
-			coherent, dir, attrs);
+	dma_handle = __iommu_dma_map(dev, phys, size, prot, dma_get_mask(dev));
 	if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
 	    dma_handle != DMA_MAPPING_ERROR)
 		arch_sync_dma_for_device(phys, size, dir);
@@ -864,7 +779,7 @@ static void iommu_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
 {
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 		iommu_dma_sync_single_for_cpu(dev, dma_handle, size, dir);
-	__iommu_dma_unmap_swiotlb(dev, dma_handle, size, dir, attrs);
+	__iommu_dma_unmap(dev, dma_handle, size);
 }
 
 /*
@@ -942,39 +857,6 @@ static void __invalidate_sg(struct scatterlist *sg, int nents)
 	}
 }
 
-static void iommu_dma_unmap_sg_swiotlb(struct device *dev, struct scatterlist *sg,
-		int nents, enum dma_data_direction dir, unsigned long attrs)
-{
-	struct scatterlist *s;
-	int i;
-
-	for_each_sg(sg, s, nents, i)
-		__iommu_dma_unmap_swiotlb(dev, sg_dma_address(s),
-				sg_dma_len(s), dir, attrs);
-}
-
-static int iommu_dma_map_sg_swiotlb(struct device *dev, struct scatterlist *sg,
-		int nents, enum dma_data_direction dir, unsigned long attrs)
-{
-	struct scatterlist *s;
-	int i;
-
-	for_each_sg(sg, s, nents, i) {
-		sg_dma_address(s) = __iommu_dma_map_swiotlb(dev, sg_phys(s),
-				s->length, dma_get_mask(dev),
-				dev_is_dma_coherent(dev), dir, attrs);
-		if (sg_dma_address(s) == DMA_MAPPING_ERROR)
-			goto out_unmap;
-		sg_dma_len(s) = s->length;
-	}
-
-	return nents;
-
-out_unmap:
-	iommu_dma_unmap_sg_swiotlb(dev, sg, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC);
-	return 0;
-}
-
 /*
  * The DMA API client is passing in a scatterlist which could describe
  * any old buffer layout, but the IOMMU API requires everything to be
@@ -1002,9 +884,6 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 		iommu_dma_sync_sg_for_device(dev, sg, nents, dir);
 
-	if (dev_is_untrusted(dev))
-		return iommu_dma_map_sg_swiotlb(dev, sg, nents, dir, attrs);
-
 	/*
 	 * Work out how much IOVA space we need, and align the segments to
 	 * IOVA granules for the IOMMU driver to handle. With some clever
@@ -1074,11 +953,6 @@ static void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 		iommu_dma_sync_sg_for_cpu(dev, sg, nents, dir);
 
-	if (dev_is_untrusted(dev)) {
-		iommu_dma_unmap_sg_swiotlb(dev, sg, nents, dir, attrs);
-		return;
-	}
-
 	/*
 	 * The scatterlist segments are mapped into a single
 	 * contiguous IOVA allocation, so this is incredibly easy.
-- 
2.32.0.605.g8dce9f2422-goog


  reply	other threads:[~2021-08-06 10:35 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-06 10:34 [PATCH v2 0/9] Add dynamic iommu backed bounce buffers David Stevens
2021-08-06 10:34 ` David Stevens [this message]
2021-08-06 10:34 ` [PATCH v2 2/9] dma-iommu: expose a few helper functions to module David Stevens
2021-08-06 17:28   ` kernel test robot
2021-08-06 10:34 ` [PATCH v2 3/9] dma-iommu: bounce buffers for untrusted devices David Stevens
2021-08-06 15:53   ` kernel test robot
2021-08-10  1:19   ` Mi, Dapeng1
2021-08-10  1:41     ` David Stevens
2021-08-06 10:34 ` [PATCH v2 4/9] dma-iommu: remove extra buffer search on unmap David Stevens
2021-08-06 10:34 ` [PATCH v2 5/9] dma-iommu: clear only necessary bytes David Stevens
2021-08-06 10:34 ` [PATCH v2 6/9] dma-iommu: add bounce buffer pools David Stevens
2021-08-06 10:34 ` [PATCH v2 7/9] dma-iommu: support iommu bounce buffer optimization David Stevens
2021-08-06 10:34 ` [PATCH v2 8/9] dma-mapping: add persistent streaming mapping flag David Stevens
2021-08-06 10:34 ` [PATCH v2 9/9] drm/i915: use DMA_ATTR_PERSISTENT_STREAMING flag David Stevens
2022-05-24 12:27 ` [PATCH v2 0/9] Add dynamic iommu backed bounce buffers Niklas Schnelle
2022-05-27  1:25   ` David Stevens
2022-06-03 14:53     ` Niklas Schnelle
2022-06-06  1:24       ` David Stevens
2022-07-01  9:23     ` Niklas Schnelle

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210806103423.3341285-2-stevensd@google.com \
    --to=stevensd@chromium.org \
    --cc=baolu.lu@linux.intel.com \
    --cc=hch@lst.de \
    --cc=iommu@lists.linux-foundation.org \
    --cc=joro@8bytes.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=robin.murphy@arm.com \
    --cc=senozhatsky@chromium.org \
    --cc=will@kernel.org \
    --subject='Re: [PATCH v2 1/9] Revert "iommu: Allow the dma-iommu api to use bounce buffers"' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).